Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    duration of a stay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ChromeDriver
    -0.66
    GEBURTSDATUM
    -0.62
    ſchen
    -0.60
    WebControls
    -0.60
     EconPapers
    -0.58
    FunctionFlags
    -0.58
    metheus
    -0.58
     NSCoder
    -0.57
    رشف
    -0.57
     électron
    -0.57
    POSITIVE LOGITS
     Stay
    1.57
     stay
    1.55
    Stay
    1.53
    stay
    1.47
     stays
    1.23
     STAY
    1.20
    STAY
    1.18
     Stays
    1.13
    stays
    1.10
     stayed
    1.05
    Act Density 0.006%

    No Known Activations